The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources (Harness IDP entities, scores, and technical documentation) which could potentially contain malicious instructions designed to influence the agent's behavior.
Ingestion points: External data is fetched using the harness_list and harness_get tools in SKILL.md to retrieve catalog metadata and score results.
Boundary markers: The instructions do not define clear delimiters or specific instructions for the agent to ignore embedded commands within the ingested content.
Capability inventory: The skill possesses capabilities to list and retrieve various IDP resources, including entities and workflows, through the Harness MCP server.
Sanitization: There is no evidence of specific sanitization, filtering, or validation of the retrieved content before it is processed or incorporated into the generated report.

scorecard-review